International Journal of Computational Intelligence and Applications

In this paper, a novel multi-scale deep residual shrinkage network (MS-DRSN) is proposed for signal denoising and atrial fibrillation (AF) recognition. Signal denoising is done by multi-scale threshold denoising module (MS-TDM), which consists of two parts: threshold acquisition and threshold denoising. The thresholds are automatically obtained through the global attention module constructed by the neural network. Threshold denoising chooses Garrote as the threshold function, which combines the advantages of soft and hard thresholding. The multi-scale features consist of global attention module and local attention module, and then the multi-scale features are denoised using the acquired thresholds and threshold functions, and the AF recognition task is finally completed in the Softmax layer after the superposition of multiple MS-TDMs. An adaptive synthetic sampling (ADASYN) algorithm is also used to oversample the dataset and achieve data category balancing by generating new samples, which improves the accuracy of AF recognition and alleviates the overfitting of the neural network. This method was experimented and validated on the PhysioNet2017 dataset. The experimental results show that the approach achieves an accuracy of 0.894 and an $F_1$ score of 0.881, which is better than current machine learning and deep learning models.

Alzheimer is an irreversible neurological disorder. It impairs the memory and thinking ability of a person. Its symptoms are not known at an early stage due to which a person is deprived of receiving medication at an early stage. Dementia, a general form of Alzheimer, is difficult to diagnose and hence a proper system for detection of Alzheimer is needed. Various studies have been done for accurate classification of patients with or without Alzheimer’s disease (AD). However, accuracy of prediction is still a challenge depending on the type of data used for diagnosis. Timely identification of true positives and false negatives are critical to the diagnosis. This work focuses on extraction of optimal features using nature-inspired algorithms to enhance the accuracy of classification models. This work proposes two hybrid nature-inspired algorithms — particle swarm optimization with genetic algorithm (PSO_GA) and whale optimization algorithm with genetic algorithm, (WOA_GA) to improve prediction accuracy. The performance of proposed algorithms is evaluated with respect to various existing algorithms on the basis of accuracy and time taken. Experimental results depict that there is trade-off in time and accuracy. Results revealed that the best accuracy is achieved by PSO_GA while it takes higher time than WOA and WOA_GA. Overall WOA_GA gives better performance accuracy when compared to a majority of the compared algorithms using support vector machine (SVM) and AdaSVM classifiers.

In this study, modeling of thin banana slices dried on 316 stainless steel shelves is carried out in an oven working with serial controlled and concentric blower-resistor couple. Changes occurred in banana slices (area and color) during drying process have been recorded by a camera. Additionally, weight has been measured with a load cell which is under the shelf and energy consumption has been measured with electricity consumption meter which is tied to energy input. The main aim of the study is to conduct the drying process of banana slices according to the data obtained from camera. Besides, obtained data have been tested with a powerful modeling technique like Artificial Neural Networks (ANN), and it has been seen that drying process could be modeled according to the data obtained from camera. Energy consumption data have been added in order to increase the performance of ANN and strengthen the modeling. Thus, an automatic drying system that can learn by itself using only a camera without any other sensors will be installed. This has been caused an increase in performance. However, it is obvious that it increases cost. According to the results of modeling process, 99% of “goodness of fit” has been obtained by using the change in banana slices and the number of pixels. It has been found that the developed model performed adequately in predicting the changes of the moisture content. Thus, it has been available to control the food drying process with a digital camera.

Clustering consists of various applications on machine learning, image segmentation, data mining and pattern recognition. The proper selection of clustering is significant in feature selection. Therefore, in this paper, a Text Feature Selection (FS) and Clustering using Grasshopper–Chameleon Swarm Optimization with Density Peaks Clustering algorithm (TFSC-G-CSOA-DPCA) is proposed. Initially, the input features are pre-processed for converting text into numerical form. These preprocessed text features are given to Grasshopper–Chameleon Swarm Optimization Algorithm, which selects important text features. In Grasshopper–Chameleon Swarm Optimization Algorithm, the Grasshopper Optimization Algorithm selects local feature from text document and Chameleon Swarm Optimization Algorithm selects the best global feature from local feature. These important features are tested using density peaks clustering algorithm to maximize the reliability and minimize the computational time cost. The performance of Grasshopper–Chameleon Swarm Optimization Algorithm is analyzed with 20 News groups dataset. Moreover, the performance metrics, like accuracy, precision, sensitivity, specificity, execution time and memory usage are analyzed. The simulation process shows that the proposed TFSC-G-CSOA-DPCA method provides better accuracy of 97.36%, 95.14%, 94.67% and 91.91% and maximum sensitivity of 96.25%, 87.25%, 93.96% and 92.59% compared to the existing methods such as TFSC-BBA-MCL, TFSC-MVO-K-Means C, TFSC-GWO-GOA-FCM and TFSC-WM-K-Means C, respectively.

Drug discovery remains a hard field that faces from the beginning of its process to the end many difficulties and challenges in order to discover a new potential drug. The use of technology has helped a lot in achieving many goals at the lowest cost and in the shortest possible time. Machine learning methods have proven for many years their performance although their limitations in some cases. The use of deep learning for virtual screening in drug discovery allows to process efficiently the huge amount of data and gives more precise results. In this paper, we propose a procedure for virtual screening (VS) based on Feedforward Neural Network in order to predict the biological activity of a set of chemical compounds on a given receptor. we have proposed a distance interval and it divisions to describe the chemical compound by the 2D pharmacophore fingerprint. Our model was trained on a dataset of active and inactive chemical compounds on cyclin A kinase1 receptor (CDK1), a very important protein family which has a role in the regulation of the cell cycle and cancer development. The results have proven that the proposed model is efficient and comparable with some widely used machine learning methods in drug discovery.

Hippocampus segmentation on magnetic resonance imaging is more significant for diagnosis, treatment and analyzing of neuropsychiatric disorders. Automatic segmentation is an active research field. Previous state-of-the-art hippocampus segmentation methods train their methods on healthy or Alzheimer’s disease patients from public datasets. It arises the question whether these methods are capable for recognizing the hippocampus in a different domain. Therefore, this study proposes a precise computational method for hippocampus segmentation from MRI of brain to assist physicians in the diagnosis of Alzheimer’s disease (HCS-MRI-DAD-LBP). Initially, the input images are pre-processed by Trimmed mean filter for image quality enhancement. Then the pre-processed images are given to ROI detection, ROI detection utilizes Weber’s law which determines the luminance factor of the image. In the region extraction process, Chan–Vese active contour model (ACM) and level sets are used (UACM). Finally, local binary pattern (LBP) is utilized to remove the erroneous pixel that maximizes the segmentation accuracy. The proposed model is implemented in MATLAB, and its performance is analyzed with performance metrics, like precision, recall, mean, variance, standard deviation and disc similarity coefficient. The proposed HCS-MRI-DAD-LBP method attains in OASIS dataset provides high disc similarity coefficient of 12.64%, 10.11% and 1.03% compared with the existing methods, like HCS-DAS-MLT, HCS-DAS-RNN and HCS-DAS-GMM and in ADNI dataset provides high precision of 20%, 9.09% and 1.05% compared with existing methods like HCS-MRI-DAD-CNN-ADNI, HCS-MRI-DAD-MCNN-ADNI and HCS-MRI-DAD-CNN-RNN-ADNI, respectively.

Due to the high ability and flexibility of meta-heuristic algorithms (MAs), they can widely be used in many applications to solve different problems. Recently, real-world engineering applications of these optimization algorithms have attracted researchers’ attention. This paper applies particle swarm optimization (PSO) as an effective population-based MAs to design the baghouse (BH). BH filters are among the most commonly used devices in air pollution control systems in mining and food manufacturers and power plants. Designing the BH depends on several parameters such as its capacity or airflow (Nm³/h), air-to-cloth ratio ($a∕c$), cam velocity, and installation limitations. Generally, industrial designers select the number and length of bags and their arrangement based on the experimental observations to meet the parameters mentioned above. The minimum cost or total weight of equipment is utilized for proposing a competitive price for suppliers. In this paper, a PSO algorithm is used to minimize the total cost by finding the best possible design (the number, length, and arrangement of bags). In addition, a real example of installed BH in a pelletizing plant is given and compared with PSO results to investigate the efficiency of the proposed algorithm. The results suggest that PSO can find a better design with minimum total cost than an installed BH filter, and therefore, PSO is applicable to industrial designers.